AI-powered pathobiology transformers predict prognosis and targeted therapy benefits in patients with colorectal cancer ovarian metastases: a multicohort study.
1/5 보강
[BACKGROUND] Individualized postoperative management of colorectal ovarian metastases demands precision medicine tools, yet current approaches lack consideration of prognostic heterogeneity and target
- p-value p<0.001
- p-value p = 0.03
- 95% CI 24.18-475.52
- HR 107.22
APA
Zhang Y, Tan D, et al. (2025). AI-powered pathobiology transformers predict prognosis and targeted therapy benefits in patients with colorectal cancer ovarian metastases: a multicohort study.. International journal of surgery (London, England). https://doi.org/10.1097/JS9.0000000000004397
MLA
Zhang Y, et al.. "AI-powered pathobiology transformers predict prognosis and targeted therapy benefits in patients with colorectal cancer ovarian metastases: a multicohort study.." International journal of surgery (London, England), 2025.
PMID
41417976 ↗
Abstract 한글 요약
[BACKGROUND] Individualized postoperative management of colorectal ovarian metastases demands precision medicine tools, yet current approaches lack consideration of prognostic heterogeneity and targeted therapy benefit guidance and suffer from high costs and long turnaround times of genetic testing.
[METHODS] In this retrospective, prospective multicohort study, we developed and validated an interpretable transformer-based transfer learning model to predict patient prognosis, targeted therapy benefits and molecular mutations by integrating digital pathology with RNA data. The performance of the model was assessed with the AUC, accuracy, sensitivity, specificity, PPV and NPV.
[RESULTS] The model accurately predicted peritoneal recurrence, with AUCs of 0.90, 0.74, and 0.83 across patient cohorts. It also achieved precise prognostic stratification for peritoneal recurrence-free survival in the training (HR = 107.22, 95% CI 24.18-475.52; p<0.001), external test (HR = 4.97, 95% CI 1.16-21.37; p = 0.03), and prospective test (HR = 10.53, 95% CI 2.02-54.94; p = 0.01) sets. The model revealed a significant association between prognostic stratification and tumor microenvironment heterogeneity (p < 0.05), thereby enhancing its biological interpretability. Further analysis revealed that only patients classified as high risk with BRAF/RAS mutations could benefit from the addition of targeted therapy to adjuvant chemotherapy (HR 0.38, 95% CI 0.18-0.79; p = 0.007). Moreover, the model predicted BRAF/RAS mutations with AUCs of 0.96/0.94 in the training set, maintaining cross-cohort generalizability with AUCs of 0.64-0.83.
[CONCLUSIONS] This pathobiology-based deep learning model can robustly detect prognosis and mutation and identify targeted therapy beneficiaries, serving as a potential precision tool in clinical decision-making for the management of colorectal ovarian metastases.
[METHODS] In this retrospective, prospective multicohort study, we developed and validated an interpretable transformer-based transfer learning model to predict patient prognosis, targeted therapy benefits and molecular mutations by integrating digital pathology with RNA data. The performance of the model was assessed with the AUC, accuracy, sensitivity, specificity, PPV and NPV.
[RESULTS] The model accurately predicted peritoneal recurrence, with AUCs of 0.90, 0.74, and 0.83 across patient cohorts. It also achieved precise prognostic stratification for peritoneal recurrence-free survival in the training (HR = 107.22, 95% CI 24.18-475.52; p<0.001), external test (HR = 4.97, 95% CI 1.16-21.37; p = 0.03), and prospective test (HR = 10.53, 95% CI 2.02-54.94; p = 0.01) sets. The model revealed a significant association between prognostic stratification and tumor microenvironment heterogeneity (p < 0.05), thereby enhancing its biological interpretability. Further analysis revealed that only patients classified as high risk with BRAF/RAS mutations could benefit from the addition of targeted therapy to adjuvant chemotherapy (HR 0.38, 95% CI 0.18-0.79; p = 0.007). Moreover, the model predicted BRAF/RAS mutations with AUCs of 0.96/0.94 in the training set, maintaining cross-cohort generalizability with AUCs of 0.64-0.83.
[CONCLUSIONS] This pathobiology-based deep learning model can robustly detect prognosis and mutation and identify targeted therapy beneficiaries, serving as a potential precision tool in clinical decision-making for the management of colorectal ovarian metastases.
🏷️ 키워드 / MeSH 📖 같은 키워드 OA만
같은 제1저자의 인용 많은 논문 (5)
- Comment on: "Interpretable machine learning model for predicting early recurrence of pancreatic cancer: integrating intratumoral and peritumoral radiomics with body composition".
- Blocking SHP2 benefits FGFR2 inhibitor and overcomes its resistance in -amplified gastric cancer.
- Impact of contrast-enhanced computed tomography surveillance frequency on survival outcomes in patients with stage I-III colorectal cancer: A propensity score-matched retrospective cohort study.
- Corrigendum to "TMEM176A drives anti-apoptotic signaling through TGM2-mediated ERK activation in gastric cancer" [Int. Immunopharmacol. 168 (2026) 115798].
- Dietary restriction genes as modulators of breast cancer risk through metabolic pathways.
🏷️ 같은 키워드 · 무료전문 — 이 논문 MeSH/keyword 기반
- Key Considerations for Targeting in Pancreatic Cancer: Potential Impact on the Treatment Paradigm.
- EXPLORING THE IMPACT OF GUT MICROBIOTA MODULATION ON COLORECTAL CANCER THERAPY: A BIBLIOMETRIC ANALYSIS OF PROBIOTIC AND PREBIOTIC INTERVENTIONS.
- Comparative evaluation of two NGS-based assays for somatic hypermutation analysis of IGHV genes in chronic lymphocytic leukemia.
- Metastatic Pancreatic Adenocarcinoma with Germline BLM and Somatic ATM Mutations: A Case Report and Review of DNA Damage Response.
- Safe discharge on the second postoperative day after major colorectal surgery: a decision-making strategy based on quantitative serological data.
- LCMS-Net: Deep Learning for Raw High Resolution Mass Spectrometry Data Applied to Forensic Cause-of-Death Screening.